yalhessi
/

lemexp-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp

Generated from Trainer

Model card Files Files and versions

yalhessi commited on Mar 15

Commit

f6d8ce8

·

verified ·

1 Parent(s): c233913

End of training

Files changed (3) hide show

README.md +1 -1
adapter_config.json +2 -2
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.001
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0001
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42

adapter_config.json CHANGED Viewed

@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20ce33783e39becb10645745809c683f93de955b233b042ba54b8c22ca97589
 size 5496

 version https://git-lfs.github.com/spec/v1
+oid sha256:53ab949c10ae7ba63431c493210572475108b01f1d56e20fd56bc36852046090
 size 5496